Listening with Language Models: Using LLMs to Collect and Interpret Classroom Feedback

2025-08-13

AI Summary

Traditional end-of-term surveys suffer from delayed, superficial, and low-actionability feedback. This paper introduces an LLM-driven conversational classroom feedback system comprising three modules—PromptDesigner, FeedbackCollector, and FeedbackAnalyzer—evaluated empirically in two graduate courses at UCSC. The system enables mid-semester, dynamic, structured, and reflective dialogue between instructors and students, overcoming the limitations of static surveys. Its key contributions are: (1) the first deep integration of LLMs into a closed-loop pedagogical feedback cycle; and (2) the use of prompt engineering and automated analytical pipelines to enhance feedback contextualization, depth, and instructional utility. Results demonstrate significantly improved student engagement and feedback quality; instructors report high adaptability and concrete pedagogical guidance; and students strongly prefer open-ended conversational formats. This work establishes a scalable, high-fidelity paradigm for data-informed teaching improvement.

Technology Category

Data Mining & Knowledge Management: Conversational Systems for Recommendation & RetrievalMachine Learning: Large Multimodal Models (LMMs)Natural Language Processing: Conversational AI/Dialog Systems

Application Category

Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved informationSemantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactionsUser Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Traditional end-of-quarter surveys often fail to provide instructors with timely, detailed, and actionable feedback about their teaching. In this paper, we explore how Large Language Model (LLM)-powered chatbots can reimagine the classroom feedback process by engaging students in reflective, conversational dialogues. Through the design and deployment of a three-part system-PromptDesigner, FeedbackCollector, and FeedbackAnalyzer-we conducted a pilot study across two graduate courses at UC Santa Cruz. Our findings suggest that LLM-based feedback systems offer richer insights, greater contextual relevance, and higher engagement compared to standard survey tools. Instructors valued the system's adaptability, specificity, and ability to support mid-course adjustments, while students appreciated the conversational format and opportunity for elaboration. We conclude by discussing the design implications of using AI to facilitate more meaningful and responsive feedback in higher education.

Problem

• Collecting timely classroom feedback using LLM chatbots
• Interpreting student feedback through conversational AI dialogues
• Replacing traditional end-of-quarter surveys with adaptive systems

Innovation

• LLM-powered chatbots for conversational feedback
• Three-part system design for feedback collection
• Real-time analysis enabling mid-course teaching adjustments